A fusion multi-target grey wolf optimization method for freshness multi-task detection of aquatic products

By combining the multi-objective gray wolf optimization algorithm with data augmentation and multi-task learning, the problems of subjectivity and low efficiency in aquatic product freshness detection are solved. It achieves simultaneous prediction and efficient detection of multiple freshness indicators, has strong adaptability, and is applicable to fields such as aquatic product processing, cold chain logistics, and market supervision.

CN121051364BActive Publication Date: 2026-02-10HEFEI UNIV OF TECH
2 Cites 0 Cited by

Patent Information

Application Number
CN202510944376.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-07-09
Publication Date
2026-02-10
Estimated Expiration
2045-07-09

AI Technical Summary

Technical Problem

Existing methods for detecting the freshness of aquatic products are subjective, destructive, and inefficient, making it difficult to meet the needs of large-scale industrial applications. Furthermore, existing infrared spectroscopy modeling methods are not adaptable to small sample scenarios, lack multi-task collaborative prediction capabilities, and have imperfect hyperparameter optimization mechanisms.

Method used

The multi-objective gray wolf optimization algorithm (MOGWO) is adopted, which combines data augmentation, CNN-LSTM-SE feature extraction and multi-task learning. The data augmentation module expands the sample size, CNN and LSTM extract spectral features in parallel, SE attention mechanism filters features, and multiple freshness indicators are predicted simultaneously through the multi-task learning framework. The MOGWO algorithm optimizes hyperparameters in stages.

Benefits of technology

It improves the accuracy, robustness, and adaptability of aquatic product freshness detection, enables simultaneous prediction of multiple freshness indicators, reduces data collection costs, improves detection efficiency and model stability, and is suitable for small sample and weak supervision conditions.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a kind of fusion multi-objective grey wolf optimization aquatic product freshness multi-task detection method, including data foundation construction, enhancement, CNN-LSTM-SE feature extraction, multi-task model formation, super parameter optimization, model training and evaluation deployment etc. steps.This method expands sample scale by data enhancement, extracts features using CNN and LSTM in parallel combined with SE attention mechanism, constructs multi-task learning framework to realize multi-index synchronous prediction, and optimizes super parameters in stages using MOGWO algorithm.The beneficial effects are to improve small sample robustness, feature extraction accuracy, multi-task detection efficiency and model generalization ability, and modular design facilitates popularization and application.
Need to check novelty before this filing date? Find Prior Art